net: ethernet: ti: am65-cpsw-nuss: Support for transparent ASEL handling

Use the glue layer's functions to convert the dma_addr_t to and from CPPI5
address (with the ASEL bits), which should be used within the descriptors
and data buffers.

- Per channel coherency support
The DMAs use the 'ASEL' bits to select data and configuration fetch path.
The ASEL bits are placed at the unused parts of any address field used by
the DMAs (pointers to descriptors, addresses in descriptors, ring base
addresses). The ASEL is not part of the address (the DMAs can address
48bits). Individual channels can be configured to be coherent (via ACP
port) or non coherent individually by configuring the ASEL to appropriate
value.

[1] https://lore.kernel.org/patchwork/cover/1350756/
Signed-off-by: Peter Ujfalusi <[email protected]>
Co-developed-by: Vignesh Raghavendra <[email protected]>
Signed-off-by: Vignesh Raghavendra <[email protected]>
Signed-off-by: Grygorii Strashko <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>

drivers/net/ethernet/ti/am65-cpsw-nuss.c

@@ -376,6 +376,7 @@ static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common,
 
 	cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
 			 AM65_CPSW_NAV_PS_DATA_SIZE);
+	k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
 	*((void **)swdata) = skb;
@@ -692,6 +693,7 @@ static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma)
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
 	skb = *swdata;
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
+	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
 
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
@@ -780,6 +782,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
 	skb = *swdata;
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
+	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
 	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
 	cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL);
 	dev_dbg(dev, "%s rx port_id:%d\n", __func__, port_id);
@@ -875,19 +878,23 @@ static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn,
 	next_desc = first_desc;
 
 	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
 
 	dma_unmap_single(tx_chn->dma_dev, buf_dma, buf_dma_len, DMA_TO_DEVICE);
 
 	next_desc_dma = cppi5_hdesc_get_next_hbdesc(first_desc);
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
 	while (next_desc_dma) {
 		next_desc = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
 						       next_desc_dma);
 		cppi5_hdesc_get_obuf(next_desc, &buf_dma, &buf_dma_len);
+		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
 
 		dma_unmap_page(tx_chn->dma_dev, buf_dma, buf_dma_len,
 			       DMA_TO_DEVICE);
 
 		next_desc_dma = cppi5_hdesc_get_next_hbdesc(next_desc);
+		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
 
 		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
 	}
@@ -1140,6 +1147,7 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 	cppi5_hdesc_set_pkttype(first_desc, 0x7);
 	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, port->port_id);
 
+	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
 	*(swdata) = skb;
@@ -1185,11 +1193,13 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 		}
 
 		cppi5_hdesc_reset_hbdesc(next_desc);
+		k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 		cppi5_hdesc_attach_buf(next_desc,
 				       buf_dma, frag_size, buf_dma, frag_size);
 
 		desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool,
 						      next_desc);
+		k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &desc_dma);
 		cppi5_hdesc_link_hbdesc(cur_desc, desc_dma);
 
 		pkt_len += frag_size;